How to Use the Linear MCP in Pydantic AI

Q: How do I initialize the Linear MCP toolset in Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset class pointing to your Vinkius MCP endpoint. Pass this toolset instance inside the toolsets argument when defining your Agent. The agent auto-discovers actions like listissues and createcomment instantly.

Q: Does this Linear MCP integration support the deprecated HTTP transport in Pydantic AI?

No, you should use the unified MCPToolset class with the server's HTTP or SSE URL. This approach handles connection lifecycles automatically, giving your Pydantic AI agent direct, stable access to tools like searchissues.

Run type-safe engineering workflows in Pydantic AI with runtime validation for every Linear ticket, comment, and cycle.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linear MCP to Pydantic AI

Create your Vinkius account to connect Linear to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Linear with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe issue creation and updates

This Linear MCP Server guarantees that every tool response matches your strict Python models at runtime. When your agent calls `create_issue`, the returned ticket payload is validated immediately, preventing corrupt or missing fields from breaking your pipeline. If the API returns unexpected priority values or malformed dates, Pydantic AI raises a validation error immediately. This loud-failure approach ensures your database remains clean and your agent never operates on hallucinated data.

Strict schema validation for this MCP Server

The server exposes tools like `get_issue` and `update_issue` with explicit parameter schemas. Your agent cannot pass bad priority integers or invalid UUIDs because the Pydantic layer checks the input structure before the API call is even made. This is crucial when updating critical fields. By forcing strict type checks on `update_issue`, you prevent models from writing invalid states or assigning issues to non-existent users.

Structured sprint and project reporting

The server uses `list_cycles` and `get_project` to supply structured data to your reporting agents. Your agent parses completion percentages and start dates directly into typed Python objects, making it easy to generate clean markdown summaries. You can also query `list_labels` to group issues by color and category. The agent uses this structured metadata to build clean dashboards, confident that every label name and description matches the expected Pydantic schema.

Setup guide

Set up Linear MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "linear-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Linear tools.",
)

result = await agent.run("List recent Linear transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Linear. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Linear now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Linear MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the `MCPToolset` class pointing to your Vinkius MCP endpoint. Pass this toolset instance inside the `toolsets` argument when defining your Agent. The agent auto-discovers actions like `list_issues` and `create_comment` instantly.

No, you should use the unified `MCPToolset` class with the server's HTTP or SSE URL. This approach handles connection lifecycles automatically, giving your Pydantic AI agent direct, stable access to tools like `search_issues`.

If the server returns data that violates your model definitions, Pydantic AI raises a validation exception. This lets you catch errors during `list_teams` or `get_viewer` execution before they propagate deeper into your application logic.

Yes, Pydantic AI is model-agnostic. You can pair this toolset with OpenAI, Anthropic, Gemini, or local models running via Ollama, letting any model query `list_projects` and manage your backlog.

Your issue descriptions, comments, and project scopes are handled through zero-trust V8 isolates. The server queries the Linear API directly, and Pydantic AI validates the response payload locally in your environment, ensuring no third party stores your raw text.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript